Turkish-English Translation Model

This model translates Turkish to English. It is based on Helsinki-NLP/opus-mt-tc-big-tr-en.

Dataset

This model uses the remox01/xde dataset which contains:

• 164 parallel sentences (Turkish-English)
• Zemberek analysis (Turkish morphological analysis)
• spaCy analysis (English POS tagging)

Usage

from transformers import AutoTokenizer, AutoModelForSeq2SeqLM

tokenizer = AutoTokenizer.from_pretrained("remox01/opus-mt-tc-big-tr-en")
model = AutoModelForSeq2SeqLM.from_pretrained("remox01/opus-mt-tc-big-tr-en")

text = "Merhaba, nasilsiniz?"
inputs = tokenizer(text, return_tensors="pt")
outputs = model.generate(**inputs)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Related Models

• remox01/opus-mt-tc-big-en-tr (English to Turkish)
• remox01/opus-mt-tc-big-tr-en-finetuned (Fine-tuned version)